A system, method, and computer-readable medium are disclosed for improved image search and retrieval. In various embodiments, a multi-image information retrieval system is implemented to perform image searching and provide image search results based on user intent. Returned image results include correlated images and associated information regarding objects such as product lines. images can include metatags and are updated with correlated information.
|
1. A computer-implementable method for image search and retrieval comprising:
receiving a search request based on an image;
searching for objects which the image describes;
determining user intent regarding the search request, wherein the user intent is correlated to a user behavior pattern by a search pattern analyzer that processes image meta data and key phrases, and wherein the user behavior pattern is determined by different ways users look for information using different key phrases related to a piece of information at any given time the piece of information appears against a specific key phrase;
providing a behavior learning implementation by implementing an n×1 approach wherein n is different ways a user looks at information and 1 is piece of information at the any given point of time and is kept static;
correlating the image with other sets of images and information related to the objects, based on the determining user intent and providing behavior implementation;
returning search results based on correlated other sets of images and information.
15. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
performing a search request based on an image;
searching for an object which the image describes;
determining user intent regarding the search request, wherein the user intent is correlated to a user behavior pattern by a search pattern analyzer that processes image meta data and key phrases, and wherein the user behavior pattern is determined by different ways users look for information using different key phrases related to a piece of information at any given time the piece of information appears against a specific key phrase;
providing a behavior learning implementation by implementing an n×1 approach wherein n is different ways a user looks at information and 1 is piece of information at the any given point of time and is kept static; based on the determining user intent and providing behavior implementation correlating the image with other images and information related to the object; returning search results based on correlated images.
8. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations for improved management of unattended user queries and comprising instructions executable by the processor and configured for:
performing an image search request;
searching for products related to the image which an image describes;
determining user intent regarding the search request, wherein the user intent is correlated to a user behavior pattern by a search pattern analyzer that processes image meta data and key phrases, and wherein the user behavior pattern is determined by different ways users look for information using different key phrases related to a piece of information at any given time the piece of information appears against a specific key phrase;
providing a behavior learning implementation by implementing an n×1 approach wherein n is different ways a user looks at information and 1 is piece of information at the any given point of time and is kept static;
based on the determining user intent and providing behavior implementation; correlating the image that the image request is based, with other images and information related to the products;
returning search results based on correlated images.
2. The method of
3. The method of
4. The method of
5. The method of
6. The method of
7. The method of
10. The system of
12. The system of
14. The system of
16. The non-transitory, computer-readable storage medium of
17. The non-transitory, computer-readable storage medium of
18. The non-transitory, computer-readable storage medium of
19. The non-transitory, computer-readable storage medium of
20. The non-transitory, computer-readable storage medium of
|
The present invention relates to the management of information handling systems. More specifically, embodiments of the invention provide a system, method, and computer-readable medium for improved image search and retrieval.
As the value and use of information continues to increase, individuals and businesses seek additional ways to process and store information. One option available to users is information handling systems. An information handling system generally processes, compiles, stores, and/or communicates information or data for business, personal, or other purposes thereby allowing users to take advantage of the value of the information. Because technology and information handling needs and requirements vary between different users or applications, information handling systems may also vary regarding what information is handled, how the information is handled, how much information is processed, stored, or communicated, and how quickly and efficiently the information may be processed, stored, or communicated. The variations in information handling systems allow for information handling systems to be general or configured for a specific user or specific use such as financial transaction processing, airline reservations, enterprise data storage, or global communications. In addition, information handling systems may include a variety of hardware and software components that may be configured to process, store, and communicate information and may include one or more computer systems, data storage systems, and networking systems.
As image searches are getting more and more popular, there is a desire to produce results that meet information requirements based on an image search, and in particular when a search originates from different search engines based on the same set of source files. One image may not provide the completeness of the information requested. For example, it would be desirable to obtain all the required images as a cluster that are in chronological order to solve a user's search purpose and link images between corresponding information. It would also be desirable to use a specific image to describe multiple parts of different solution workflows. Although there may be different methods and strategies that are directed to image searching, such strategies may only focus on an image file, and are not directed to image and content correlation.
When a user conducts an image search query for a particular product or products, the search results may return the wrong image and/or unwanted information. The returned image and information may not include relevant information that is based on the search query. The image may be misleading, be too generic, or associated with misleading information or no information. For example, if a user performs an image search query for a particular server computer, the search results may be generic images and irrelevant information regarding the particular server computer.
Certain image search strategies may be specific to particular search engines, web browsers, and databases. Such strategies may only be implemented through specific user interfaces. Typically, such search strategies make guesses as to text associated with images. Indexing or use of standard metadata is not implemented with such image searching. Other image search strategies do not provide for a change in representation based on a user's persona and intent. Such search strategies typically cluster images based on a minimum match that is found on search strings, and potential images are grouped together.
A system, method, and computer-readable medium are disclosed for improved image search and retrieval. In various embodiments, a multi-image information system is implemented to perform image searching and provide image search results based user intent. Returned image results include correlated images and information regarding objects such as product lines. Images can include metatags and are updated with correlated information.
In various embodiments, search request are received base on an image. Searches are performed for objects that the image describes. User intent is determined as to the search request. Correlation is performed with the other images and information that are related to targets, identified objects, topics, products, technology, etc. Results are returned which can include information such as workflow solutions.
The present invention may be better understood, and its numerous objects, features and advantages made apparent to those skilled in the art by referencing the accompanying drawings. The use of the same reference number throughout the several figures designates a like or similar element.
A system, method, and computer-readable medium are disclosed for image search and retrieval. For purposes of this disclosure, an information handling system may include any instrumentality or aggregate of instrumentalities operable to compute, classify, process, transmit, receive, retrieve, originate, switch, store, display, manifest, detect, record, reproduce, handle, or utilize any form of information, intelligence, or data for business, scientific, control, or other purposes. For example, an information handling system may be a personal computer, a network storage device, or any other suitable device and may vary in size, shape, performance, functionality, and price. The information handling system may include random access memory (RAM), one or more processing resources such as a central processing unit (CPU) or hardware or software control logic, ROM, and/or other types of nonvolatile memory. Additional components of the information handling system may include one or more disk drives, one or more network ports for communicating with external devices as well as various input and output (I/O) devices, such as a keyboard, a mouse, and a video display. The information handling system may also include one or more buses operable to transmit communications between the various hardware components.
In certain embodiments, the multi-image information retrieval system 118 includes a web crawler/agent 202. Web crawler/agent 204 can be configured to interact with different sites, platforms, or environments that can include vendor support sites, social media sites, data repositories, etc. Such sites, platforms, or environments are represented as environment ‘1’ 204 through environment ‘n’ 206. The environment ‘1’ 204 through environment ‘n’ 206 can include different images of the same product or product line. The web crawler/agent 202 can be configured to crawl through the different images of the same product or product line resident on environment ‘1’ 204 through environment ‘n’ 206. The web crawler/agent 202 can include or be configured to an internal tracker 208 which can be used to describe end to end workflows based on image metadata and embedded text within the images. The end to end workflows can be described by one or more images. Metadata is data or information that provides information as to other data. Metadata may be written in an image and provide information as to that image.
In certain embodiments, the multi-image information retrieval system 118 includes one or more search engines 210. Image searching can be performed on different search engines of the one or more search engines 210, where the image searching is based on the same set of source files. The multi-image information retrieval system 118 can include one or more image sitemaps 212. In certain implementations, when a set of images is identified as a work flow, the image sitemaps 212 is/are updated with hints and clues as to image retrieval. Sitemaps 212 can be implemented to accommodate image related data, such as metadata associated with images. Sitemaps 212 can be used to inform the search engines 210 as to uniform resource locators (URL) of websites that are available for crawling. Furthermore, additional information regarding the URLs can be provided by sitemaps 212.
It is desirable to understand users' intent as to search queries, and to provide a behavior learning implementation. Information can be consumed in many ways; however, users' behaviors are different and can vary based on request factors and search terms, although information is constant. By taking an “n” by “1” (i.e., n×1) approach, where “n” is the different ways that users are looking for information, with different key phrases that are used for a specific search, and “1” is a piece of information, at any given point of time which information is appearing as a search result against a specific key phase). Since “n” is not constant, an algorithm is implemented that can learn and re-learn users' behavior patterns over a period of time, where the information is kept static/same. This can be a continuous process that analyzes information consumed during user sessions against a business-driven logical structure and a product driven theme structure. In addition, the process performs analysis on segmentation of each information set that is consumed/used.
In certain embodiments, in order to meet users' search queries when such searches are image based, the following are implemented by the multi-image information retrieval system 118. In certain implementations, a search pattern analyzer 214 processes information data from users' image search sessions. In particular, the search pattern analyzer 214 is configured to process image metadata, which includes key phrases that searched that are correlated to different user behavior patterns and associated with users' intents. The search pattern analyzer 214 is further configured to process content that appears during different string or text searches. A text to intent analyzer 216 receives information/data from the search pattern analyzer 214. The text to intent analyzer 216 can be implemented to segregate text based on a user's persona or intent, and keep an association based on the link to an image.
In this implementation, the search pattern analyzer 214 further provides information/data to a user persona engine 218 directed to user intent. The user persona engine 218 processes particular user persona using information/data from canned or predetermined behavior patterns 220 and can also modify such user persona based on information/data from the search pattern analyzer 214. Information as to user persona can change based on image searches.
In this implementation, an image metadata handler engine 222 receives images with information/data from the text to intent analyzer 216 and users' persona from the user persona engine 218. The image metadata handler engine 222 can be configured to correlate image metadata with associated text for different user behavior patterns. The image metadata handler engine 222 provides images 224 that include image metadata that have user persona describing user behavior patterns. The images 224 can be stored in meta-tagged images 226. The meta-tagged images 226 include images of a meta-tagged corpus of unique responses for different user types/persona. For certain implementations, images from meta-tagged images 226 can be sent to the image metadata handler engine 222 for continued processing. Therefore, personalized content searching can be provided through image searching based on users' profiles and intent. In addition, information infrastructures can be enabled with image driven content with dynamic responses based on search strings and users' persona.
In certain embodiments, the multi-image information retrieval system 118 includes a content correlation manager 228. The content correlation manager 228 can be configured to correlate relevant images with text content, and correlate images to one another or with a set of images.
For example, a business may have several products or product lines. In an implementation, an image database 302 and document corpus 304 is provided. The image database 302 includes images of the products or product lines. The image database 302 includes images that may be linked to pages which are static placements. The images of image database 302 may not have any metadata information which correlates the images to content of the pages or other images of the pages. Document corpus 304 includes documents that may relate to images of image database 302.
In an implementation, a correlation mapper 308 receives information from a correlation knowledge base 310, where the information allows the correlation mapper 308 to map images of image database 302 with documents/pages in document corpus 304. In particular, the correlation knowledge base 310 includes data for content or images and relationship of the content or images to document/pages.
The correlation mapper 308 can create a hierarchy tree that creates a correlation of the images of image database 302 with the content of document/pages document corpus 302.
Referring back to
By implementing the processes described, during image searching, image and content correlation and representation of associated textual information can be provided. In addition, hierarchical and structure metadata identification for images can be associated with correlated information from different sources.
In these and other embodiments, the user 502 may use a user device(s) 504 to search for images and related documents/information from multi-image information system 118. As used herein, user device(s) 504 refers to an information handling system such as a personal computer, a laptop computer, a tablet computer, a personal digital assistant (PDA), a smart phone, a mobile telephone, or other device that is capable of communicating and processing data. In various embodiments, the user device(s) 504 is used to exchange information between the information handling system 100 through the use of a network 140. In certain embodiments, the network 140 may be a public network, such as the Internet, a physical private network, a wireless network, a virtual private network (VPN), or any combination thereof. Skilled practitioners of the art will recognize that many such embodiments are possible and the foregoing is not intended to limit the spirit, scope or intent of the invention.
In certain implementations, the information handling system 100 includes the image database 302, the document corpus 304, the correlation knowledge base 310, and correlated images 316. The multi-image information system 118 can access the image database 302, the document corpus 304, the correlation knowledge base 310, and correlated images 316.
In certain implementations, business unit ‘1” 506 through business unit ‘n’ 508 interact with user 502. Business unit 1″ 506 through business unit ‘n’ 508 can be administrators of multi-image information system 118. Business unit 1″ 506 through business unit ‘n’ 508 may implement or administer the multi-image information system 118 to provide image searching and retrieval to the user 502. Communication by business unit 1″ 506 through business unit ‘n’ 508 can be through network 140 through respective business system ‘1’ 510 through business system ‘n’ 512. In certain embodiments, the business unit 1″ 506 through business unit ‘n’ 508 can include an information design and development unit or group that provides for illustrations (i.e., images) across multiple geographic and product lines, producing images for documents. The documents can be used of enterprise, client, consumer, networking, etc. Such images can convey complex information which are specific to systems and can be reused for multiple use case scenarios. For such a business unit or group such as information design and development, it is desirable to assure that related images appear during image searching as a cluster along with relevant content/information.
As discussed above in reference to
Image metadata information can include the following, where such metadata information can be used in updating an image sitemap(s). The Meta Tag <image:image.filename> may be required, describes the file name identifier for indexing, and has no associated metadata. The Meta Tag <image:source> may be required, is a multiple source of the same image and can potentially harm indexing as can confuse a web crawler (e.g. web crawler/agent 202), therefore source is locked for a particular image, and has associated metadata than can include source pages where the image is reused (e.g, <url 1>, <url 2> . . . <url n>). The Meta Tag <image:title> may be required, is a title for a specific image, and can have associated metadata to a stack of the scenarios where the image can be utilized. The Meta Tag <image:geo_location> may not be required, describes geographical limitations, and can have associated metadata and is open to allow for information to be consumed from various sources.
Now referring to
At block 702, process 700 starts. At step 704 an image search request is received. The image search request can be an image search query based on a particular image. At step 706, a search for objects, such as products or product lines is performed, where the image describes objects (e.g., the products or product lines). At step 708, a determination is performed as to user intent regarding the image search. A user intent can include searching for workflow solutions regarding a product or product line. At step 710, correlation is performed as to the objects and image with other images and other information based on the user intent. At step 712, results are returned that provide correlated images and other information. At block 714, process 700 ends.
The present invention is well adapted to attain the advantages mentioned as well as others inherent therein. While the present invention has been depicted, described, and is defined by reference to particular embodiments of the invention, such references do not imply a limitation on the invention, and no such limitation is to be inferred. The invention is capable of considerable modification, alteration, and equivalents in form and function, as will occur to those ordinarily skilled in the pertinent arts. The depicted and described embodiments are examples only, and are not exhaustive of the scope of the invention.
As will be appreciated by one skilled in the art, the present invention may be embodied as a method, system, or computer program product. Accordingly, embodiments of the invention may be implemented entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in an embodiment combining software and hardware. These various embodiments may all generally be referred to herein as a “circuit,” “module,” or “system.” Furthermore, the present invention may take the form of a computer program product on a computer-usable storage medium having computer-usable program code embodied in the medium.
Any suitable computer usable or computer readable medium may be utilized. The computer-usable or computer-readable medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, or a magnetic storage device. In the context of this document, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
Computer program code for carrying out operations of the present invention may be written in an object oriented programming language such as Java, Smalltalk, C++ or the like. However, the computer program code for carrying out operations of the present invention may also be written in conventional procedural programming languages, such as the “C” programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).
Embodiments of the invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The present invention is well adapted to attain the advantages mentioned as well as others inherent therein. While the present invention has been depicted, described, and is defined by reference to particular embodiments of the invention, such references do not imply a limitation on the invention, and no such limitation is to be inferred. The invention is capable of considerable modification, alteration, and equivalents in form and function, as will occur to those ordinarily skilled in the pertinent arts. The depicted and described embodiments are examples only, and are not exhaustive of the scope of the invention.
Consequently, the invention is intended to be limited only by the spirit and scope of the appended claims, giving full cognizance to equivalents in all respects.
Mathew, Thomas, Roy, Mainak, Gupta, Chitrak, Babu, Rathi, Moncy, Lavy T., Boovaraha, Upendran
Patent | Priority | Assignee | Title |
Patent | Priority | Assignee | Title |
10664515, | May 29 2015 | Microsoft Technology Licensing, LLC | Task-focused search by image |
9779187, | Aug 26 2013 | Fair Isaac Corporation | Automatic modeling farmer |
20150161178, | |||
20190121808, |
Date | Maintenance Fee Events |
Feb 27 2019 | BIG: Entity status set to Undiscounted (note the period is included in the code). |
Date | Maintenance Schedule |
Aug 09 2025 | 4 years fee payment window open |
Feb 09 2026 | 6 months grace period start (w surcharge) |
Aug 09 2026 | patent expiry (for year 4) |
Aug 09 2028 | 2 years to revive unintentionally abandoned end. (for year 4) |
Aug 09 2029 | 8 years fee payment window open |
Feb 09 2030 | 6 months grace period start (w surcharge) |
Aug 09 2030 | patent expiry (for year 8) |
Aug 09 2032 | 2 years to revive unintentionally abandoned end. (for year 8) |
Aug 09 2033 | 12 years fee payment window open |
Feb 09 2034 | 6 months grace period start (w surcharge) |
Aug 09 2034 | patent expiry (for year 12) |
Aug 09 2036 | 2 years to revive unintentionally abandoned end. (for year 12) |